OpenSidewalkMap Statistics

About: this statistics are compilated with Sidewalks,Crossings and Kerbs data.

All the code is kept here, so anyone can reproduce!


Scroll down and the charts will begin to appear, they we're made with the amazing Altair library, that enables interactivity


Sidewalks Statistics
Crossings Statistics
Kerbs Statistics

currently it's only optimized for desktop

The Jupyter Notebook is avaliable Here

In [1]:
from datetime import datetime 

now = datetime.now()
dt_string = now.strftime("%d/%m/%Y %H:%M:%S")
print('Last Update: ',dt_string)

Last Update:  05/07/2022 13:11:49
In [2]:
import geopandas as gpd
import pandas as pd
import altair as alt
In [3]:
def get_count_df(input_df,fieldname,str_to_append=' type'):
    outfieldname = fieldname+str_to_append
    return input_df[fieldname].value_counts().reset_index().rename(columns={'index':outfieldname,fieldname:'count'}).sort_values(by='count',ascending=False),outfieldname

def create_barchart(input_df,fieldname,title,str_to_append=' type',title_fontsize=24,tooltip='count',x_sort='-y',tooltip_list=['percent']):
    # bind = alt.selection_interval(bind='scales')
    # .add_selection(bind)

    data_to_plot,fieldname_v2 = get_count_df(input_df,fieldname,str_to_append)

    feat_count = float(data_to_plot['count'].sum())

    def compute_formatted_percent(featureval):
        return str(round((featureval/feat_count)*100,2))+"%"

    data_to_plot['percent'] = data_to_plot['count'].apply(compute_formatted_percent)

    return alt.Chart(data_to_plot,title=title).mark_bar().encode(
        x=alt.X(fieldname_v2,sort=x_sort),
        y='count',
        tooltip=tooltip_list,
    ).properties(
    width=650,
    height=300).configure_title(fontSize=title_fontsize).interactive()

def create_barchartV2(input_gdf,fieldname,title,str_to_append=' type',title_fontsize=24,len_field='length(km)'):

    # bind = alt.selection_interval(bind='scales')
    # .add_selection(bind)

    fieldname_v2 = fieldname+str_to_append

    data_to_plot = input_gdf[[len_field,fieldname]].groupby([fieldname]).agg({fieldname:'count',len_field:'sum'}).rename(columns={fieldname:'feature count'}).reset_index().rename(columns={fieldname:fieldname_v2})

    return alt.Chart(data_to_plot,title=title).mark_bar().encode(
        x=alt.X(fieldname_v2,sort='-y'),
        y=len_field,
        tooltip=len_field,
        color='feature count'
    ).properties(
    width=650,
    height=300).configure_title(fontSize=title_fontsize).interactive()

def print_relevant_columnames(input_df,not_include=('score','geometry','type','id')):
    print(*[f'{column}, ' for column in input_df.columns if not any(word in column for word in not_include)])

def return_weblink(string_id,type='way'):
    return f"<a href=https://www.openstreetmap.org/{type}/{string_id}>{string_id}</a>"

def get_year_surveydate(featuredate):
    return featuredate.split('-')[0]

SIDEWALKS STATISTICS¶

In [4]:
sidewalks_gdf = gpd.read_file('../data/sidewalks.geojson')
sidewalks_data = pd.DataFrame(sidewalks_gdf)
In [5]:
# compute lengths only once:
sidewalks_gdf['length(km)'] = sidewalks_gdf.to_crs('EPSG:31982').length/1000

sidewalks_gdf['weblink'] = sidewalks_gdf['id'].astype('string').apply(return_weblink)

sidewalks_gdf['Year of Survey'] = sidewalks_gdf['survey:date'].apply(get_year_surveydate)
In [6]:
# sidewalk Length Statistics
sidewalks_gdf['length(km)'].describe()
Out[6]:
count    1990.000000
mean        0.080533
std         0.158999
min         0.000935
25%         0.012500
50%         0.025342
75%         0.064382
max         2.852458
Name: length(km), dtype: float64

printing relevant columns on the data:

In [7]:
print_relevant_columnames(sidewalks_gdf)

bicycle,  footway,  highway,  name,  foot,  lcn,  motor_vehicle,  segregated,  access,  horse,  oneway,  mapillary,  maxspeed,  survey:date,  tactile_paving,  layer,  lit,  surface,  tunnel,  incline,  smoothness,  opening_hours,  cutting,  embankment,  dog,  wheelchair,  level,  cycleway,  cycleway:right,  ramp,  noname,  crossing,  alt_name,  source,  handrail,  ramp:wheelchair,  step_count,  kerb,  traffic_signals,  description,  paving_stones,  barrier,  incline:across,  length(km),  weblink,  Year of Survey,
In [8]:
create_barchartV2(sidewalks_data,'surface','Sidewalks Surface Type',title_fontsize=24)
Out[8]:
In [ ]:
create_barchartV2(sidewalks_data,'smoothness','Sidewalks Smoothness Level',title_fontsize=24)
In [ ]:
create_barchartV2(sidewalks_data,'tactile_paving','Sidewalks Tactile Paving Presence',title_fontsize=24)
Out[ ]:
In [ ]:
create_barchartV2(sidewalks_data,'width','Sidewalks Width Values',title_fontsize=24)
Out[ ]:
In [ ]:
create_barchartV2(sidewalks_data,'incline','Sidewalks Incline Values',title_fontsize=24)
Out[ ]:
In [ ]:
def double_scatter_bar(input_df,title,xs='surface',ys='smoothness',scolor=None,xh='count()',yh1='surface',yh2='smoothness',hcolor=None,fontsize=24,tooltip_fields=['type','id']):

    interval = alt.selection_interval()

    default_color = alt.value('lightseagreen')

    if not hcolor:
        hcolor = default_color

    if not scolor:
        scolor = default_color


    scatter = alt.Chart(input_df,title=title).mark_point().encode(
        x=xs,
        y=ys,
        color=scolor,
        tooltip=alt.Tooltip(tooltip_fields),
    ).properties(
    width=600,
    height=350,).add_selection(interval)

    hist_base = alt.Chart(input_df).mark_bar().encode(
        x=xh,
        color=hcolor,
        tooltip=alt.Tooltip(tooltip_fields),
        

    ).properties(
        width=300,
        height=220,
    ).transform_filter(
        interval,
    )

    # if hcolor:
    #      hist_base.encode(color=hcolor)

    hist = hist_base.encode(y=yh1) | hist_base.encode(y=yh2)

    return (scatter & hist).configure_title(fontSize=fontsize,align='center')

# 'Surface x Smoothness'
In [ ]:
double_scatter_bar(sidewalks_gdf,'Surface x Smoothness (sidewalks)',hcolor='length(km)')
Out[ ]:
In [ ]:
create_barchart(sidewalks_gdf,'Year of Survey','Year of Survey Image (sidewalks)')
Out[ ]:
In [ ]:
# updating info:
sidewalks_updating = pd.read_json('../data/sidewalks_versioning.json')
crossings_updating = pd.read_json('../data/crossings_versioning.json')
kerbs_updating = pd.read_json('../data/kerbs_versioning.json')

updating_dict = {'sidewalks':sidewalks_updating,'crossings':crossings_updating,'kerbs':kerbs_updating}
In [ ]:
# crating month_year field:

for category in updating_dict:

    updating_dict[category]['month_year'] = updating_dict[category]['rev_month'].map("{:02d}".format) + '_' + updating_dict[category]['rev_year'].astype(str)

    updating_dict[category]['year_month'] =  updating_dict[category]['rev_year'].astype(str) + "_" + updating_dict[category]['rev_month'].map("{:02d}".format)


    updating_dict[category].sort_values('year_month',inplace=True)
In [ ]:
print_relevant_columnames(sidewalks_updating,not_include=[])

osmid,  rev_day,  rev_month,  rev_year,  n_revs,  month_year,  year_month,
In [ ]:
create_barchart(sidewalks_updating,'year_month','Year and Month Of Update (Sidewalks)',x_sort='-x')
Out[ ]:
In [ ]:
create_barchart(sidewalks_updating,'n_revs','Number Of Revisions (Sidewalks)',x_sort='-x')
Out[ ]:

CROSSINGS STATISTICS¶

In [ ]:
crossings_gdf = gpd.read_file('../data/crossings.geojson')
crossings_data = pd.DataFrame(crossings_gdf)
In [ ]:
# compute lengths only once:
crossings_gdf['length(km)'] = crossings_gdf.to_crs('EPSG:31982').length/1000

crossings_gdf['weblink'] = crossings_gdf['id'].astype('string').apply(return_weblink)

crossings_gdf['Year of Survey'] = crossings_gdf['survey:date'].apply(get_year_surveydate)
In [ ]:
print_relevant_columnames(crossings_gdf)

crossing,  footway,  highway,  kerb,  surface,  tactile_paving,  traffic_calming,  bicycle,  name,  foot,  lit,  segregated,  layer,  access,  alt_name,  horse,  note,  motor_vehicle,  incline,  lcn,  crossing:island,  lanes,  oneway,  level,  cycleway,  cycleway:right,  smoothness,  wheelchair,  mapillary,  survey:date,  barrier,  length(km),  weblink,  Year of Survey,
In [ ]:
create_barchart(crossings_gdf,'crossing','Crossing Type')
Out[ ]:
In [ ]:
create_barchart(crossings_gdf,'surface','Crossing Surface')
Out[ ]:
In [ ]:
double_scatter_bar(crossings_gdf,'Surface x Smoothness (crossings)',
hcolor='crossing',
# scolor='crossing',
)
Out[ ]:
In [ ]:
create_barchart(crossings_gdf,'Year of Survey','Year of Survey Image (crossings)')
Out[ ]:
In [ ]:
create_barchart(crossings_updating,'year_month','Year and Month Of Update (Crossings)',x_sort='-x')
Out[ ]:
In [ ]:
create_barchart(crossings_updating,'n_revs','Number Of Revisions (Crossings)',x_sort='-x')
Out[ ]:

KERBS STATISTICS¶

In [ ]:
kerbs_gdf = gpd.read_file('../data/kerbs.geojson')
kerbs_data = pd.DataFrame(kerbs_gdf)
In [ ]:
kerbs_gdf['Year of Survey'] = kerbs_gdf['survey:date'].apply(get_year_surveydate)
In [ ]:
print_relevant_columnames(kerbs_gdf)

crossing,  crossing_ref,  highway,  kerb,  tactile_paving,  traffic_calming,  bicycle,  mapillary,  survey:date,  wheelchair,  button_operated,  traffic_signals:sound,  traffic_signals:vibration,  crossing:island,  image,  barrier,  surface,  kerb:height,  traffic_signals,  smoothness,  description,  Year of Survey,
In [ ]:
create_barchart(kerbs_gdf,'kerb','Kerb Type')
Out[ ]:
In [ ]:
create_barchart(kerbs_gdf,'tactile_paving','Kerb Tactile Paving Presence')
Out[ ]:
In [ ]:
create_barchart(kerbs_gdf,'wheelchair','Kerb Wheelchair Acessibility')
Out[ ]:
In [ ]:
create_barchart(kerbs_gdf,'kerb:height','Kerb Height')
Out[ ]:
In [ ]:
create_barchart(kerbs_gdf,'Year of Survey','Year of Survey Image (kerbs)')
Out[ ]:
In [ ]:
double_scatter_bar(kerbs_gdf,' ',xs='kerb',ys='tactile_paving',yh1='kerb',yh2='tactile_paving',xh='count()',hcolor='wheelchair')
Out[ ]:
In [ ]:
create_barchart(kerbs_updating,'year_month','Year and Month Of Update (Kerbs)',x_sort='-x')
Out[ ]:
In [ ]:
create_barchart(kerbs_updating,'n_revs','Number Of Revisions (Kerbs)',x_sort='-x')
Out[ ]:
In [ ]:
import sys
sys.path.append('..')
In [ ]:
from time import sleep
from functions import record_datetime,gen_updating_infotable_page

# to record data aging:
record_datetime('Statistical Charts','../data/last_updated.json')
sleep(.1)

# generate the "report" of the updating info
gen_updating_infotable_page('../data/data_updating.html','../data/last_updated.json')
In [ ]:
!jupyter nbconvert --to html statistics.ipynb

[NbConvertApp] Converting notebook statistics.ipynb to html
[NbConvertApp] Writing 4131388 bytes to statistics.html